%0 Journal Article
%T THE EXPECTED AVERAGE CRITERION FOR NONSTATIONARY MDP
非平稳MDP的期望平均准则
%A Xian Ping GUO
%A Zhen Ting HOU
%A
郭先平
%A 侯振挺
%J 系统科学与数学
%D 1999
%I
%X In this paper, we consider the expected average criterion for nonstationary MDP. By probability and martingale method, we prove the existence of #epsilon#(>=0)-optimal Markov policies under weakly ergodic conditions. As a typical example of this paper, we solve the open problem posed by Feinberg and Park again.
%K Markov decision processes
%K expected average criterion
%K optimal equation
%K optimal policy
马氏决策过程(MDP)
%K 期望平均准则
%K 最优方程
%K 最优策略
%U http://www.alljournals.cn/get_abstract_url.aspx?pcid=6E709DC38FA1D09A4B578DD0906875B5B44D4D294832BB8E&cid=37F46C35E03B4B86&jid=0CD45CC5E994895A7F41A783D4235EC2&aid=22D03C8E4CCB38D2&yid=B914830F5B1D1078&vid=2A8D03AD8076A2E3&iid=CA4FD0336C81A37A&sid=AE09EACBCD1B2A13&eid=1F199509C0B6C4D6&journal_id=1000-0577&journal_name=系统科学与数学&referenced_num=0&reference_num=0